Advanced Skills by Learning Locomotion and Local Navigation End-to-End

09/26/2022
by   Nikita Rudin, et al.
0

The common approach for local navigation on challenging environments with legged robots requires path planning, path following and locomotion, which usually requires a locomotion control policy that accurately tracks a commanded velocity. However, by breaking down the navigation problem into these sub-tasks, we limit the robot's capabilities since the individual tasks do not consider the full solution space. In this work, we propose to solve the complete problem by training an end-to-end policy with deep reinforcement learning. Instead of continuously tracking a precomputed path, the robot needs to reach a target position within a provided time. The task's success is only evaluated at the end of an episode, meaning that the policy does not need to reach the target as fast as possible. It is free to select its path and the locomotion gait. Training a policy in this way opens up a larger set of possible solutions, which allows the robot to learn more complex behaviors. We compare our approach to velocity tracking and additionally show that the time dependence of the task reward is critical to successfully learn these new behaviors. Finally, we demonstrate the successful deployment of policies on a real quadrupedal robot. The robot is able to cross challenging terrains, which were not possible previously, while using a more energy-efficient gait and achieving a higher success rate.

READ FULL TEXT

page 1

page 3

page 5

page 6

research
05/22/2019

Hierarchical Reinforcement Learning for Quadruped Locomotion

Legged locomotion is a challenging task for learning algorithms, especia...
research
08/06/2023

Learning Multiple Gaits within Latent Space for Quadruped Robots

Learning multiple gaits is non-trivial for legged robots, especially whe...
research
11/03/2016

Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?

The use of deep reinforcement learning allows for high-dimensional state...
research
10/26/2022

ViNL: Visual Navigation and Locomotion Over Obstacles

We present Visual Navigation and Locomotion over obstacles (ViNL), which...
research
07/27/2022

PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations

Evolution Strategy (ES) algorithms have shown promising results in train...
research
09/09/2021

Learning Vision-Guided Dynamic Locomotion Over Challenging Terrains

Legged robots are becoming increasingly powerful and popular in recent y...
research
12/09/2021

Learning multiple gaits of quadruped robot using hierarchical reinforcement learning

There is a growing interest in learning a velocity command tracking cont...

Please sign up or login with your details

Forgot password? Click here to reset